2,667 reputation
1321
bio website
location
age
visits member for 2 years, 4 months
seen 6 hours ago

I'm the Rose part of:

Rose, C. and Smith, M.D. (2002-2013)
Mathematical Statistics with Mathematica
Springer-Verlag / mathStatica

and one of the original developers of the mathStatica software add-on for Mathematica. I'm a long-time Mma fan since v2, ... a past Visiting Scholar at Wolfram Research, ... a recent guest editor of The Mathematica Journal, ... and a current editor of the Journal of Statistical Software.


Aug
10
comment Expected sum of largest 3
Umm -- the solution given here using OrderDistribution is correct by chance, but the approach is not actually valid. In particular, it defines a as the distribution of the largest order statistic, b as the second largest ... etc ... each univariate ... BUT what is actually needed is the joint pdf of $(a,b,c)$ ... not the marginal pdfs of a, b and c. The solution happens to work in this particular instance, not because the method is correct, but because $E[a + b + c] = E[a] + E[b] + E[c]$. By contrast, the proposed method would give the wrong answer for: Expectation[a b c, etc]
Aug
7
comment Simulation Beta Distribution
OP notes that $X\sim Beta$ ... which is a continuous random variable. It is not stated what $y$ is, but if $y$ is a constant, or $y$ is an independent random variable, then $P(X=y) = 0$. If so, you can ignore the case $X = y$, because it happens with zero probability.
Aug
6
comment Mma 10: Half the parallel power (Macs)?
It's an observation, a workaround, and an empirical check. I would hope it is helpful to others. I would prefer to keep the question as is. But please do not let that discourage you from modifying your answer, because I am sure many would be interested in alternative parallel kernel speed comparisons.
Aug
6
comment Problem with Maximize
If your function is sufficiently messy, you may need to try using FindMaximum instead, noting that it finds local maxima, depending on where you start the search. But then, NMaximize may also yield local maxima.
Aug
6
comment Mma 10: Half the parallel power (Macs)?
@Szabolcs Mostly, I think your existing answer "this is an intentional and beneficial change in v10" would benefit from some form of substantiation in support of the claim.
Aug
6
comment Mma 10: Half the parallel power (Macs)?
@Szabolcs I am quite happy with the question as it stands: it is fairly concise and it covers the main issues. If you would like to delete your answer, or modify your answer to improve it, ... that is of course up to you. The issue of v10 performance versus v9 performance is entirely another question -- not this one. Nor is it dealt with here. If you would like to focus on how the number of kernels affects performance, that could be very nicely done within your answer (I look forwards to seeing alternative calculations), or even as a separate self-contained answer.
Aug
5
comment Which Distributions can be Compiled using RandomVariate
Since the results of RandomVariate are ALWAYS going to be Reals (for a continuous distribution), and Integers (for most inbuilt discrete distributions), I can't see why there would be any advantage to compiling them, that could not have automatically been built into the function. Does anyone have some timing tests where manual compilation yields substantive benefits to something like: RandomVariate[ dist, {10^6}] ?
Aug
4
reviewed Approve suggested edit on Failure to export graphics by right-click when Notebook magnification is changed
Aug
2
comment Manual maximum likelihood estimation of a mixture with no closed form
For starters, your mix[ ] function is supposed to be a mix of two Lognormals, but you have actually set it up as a mix of a Normal and a Lognormal. Another case of using blackbox functions, and not checking intermediate output. Second, there should be no need to use approximating functions in Mma. Third, your question is far too long and convoluted to get to the essence ...
Aug
1
reviewed Approve suggested edit on Efficient Way to Check Polynomial Irreducibility
Jul
31
revised Mma 10: Half the parallel power (Macs)?
Added more detailed real world test using full mathStatica benchmark suite under v10
Jul
29
comment Conditional Expectation — How can Mathematica find a more general closed form?
@SethChandler If you also wish to generalise $X \sim Uniform(0,1)$ to $X \sim Uniform(a,b)$ ... since you have $1-X$, do you not need to assume that $0<x<1$ i.e. that $0\le a <b \le1 $?
Jul
29
comment Conditional Expectation — How can Mathematica find a more general closed form?
@SethChandler Hi Seth. Yes - mathStatica is fully compatible with v10. As to the general cases, have just tried: ...... f = 1/(d - c); domain[f] = {{x, 0, 1}, {y, c, d}} && {0 < c < d}; ... and that works perfectly, just following exactly the same steps.
Jul
28
revised Conditional Expectation — How can Mathematica find a more general closed form?
Suggest adding probability tag
Jul
28
reviewed Approve suggested edit on Creating a new list by dropping sub elements of the original list
Jul
28
reviewed Approve suggested edit on Using select to pick out elements of nested lists in an odd way
Jul
28
revised Conditional Expectation — How can Mathematica find a more general closed form?
added 40 characters in body
Jul
28
comment Conditional Expectation — How can Mathematica find a more general closed form?
Hi @SethChandler - I've added a second answer: the tweak you seek. :)
Jul
28
answered Conditional Expectation — How can Mathematica find a more general closed form?
Jul
27
revised Conditional Expectation — How can Mathematica find a more general closed form?
deleted 13 characters in body